selenium-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SMCP_DEBUG | No | Verbose debug logging (true/false). | false |
| SMCP_BROWSER | No | Default browser (chrome/firefox). | chrome |
| SMCP_HEADLESS | No | Run headless (true/false). | true |
| SMCP_LOG_LEVEL | No | Log level (e.g., INFO, DEBUG). | INFO |
| SMCP_CONFIG_FILE | No | Path to custom YAML config file. | |
| SMCP_BIDI_ENABLED | No | Enable BiDi WebSocket (true/false). | true |
| SMCP_MAX_SESSIONS | No | Max concurrent sessions. | 5 |
| SMCP_SCREENSHOT_DIR | No | Screenshot output directory. | screenshots/ |
| SMCP_SCREENSHOT_ON_ERROR | No | Auto-screenshot on errors (true/false). | true |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| create_sessionC | Create a new browser session. Defaults to Chrome headless. |
| close_sessionC | Close a browser session by ID. |
| list_sessionsA | List all active browser sessions. |
| get_session_infoC | Get metadata for a browser session. |
| open_pageC | Navigate the browser to a URL. |
| navigate_backC | Go back in browser history. |
| navigate_forwardC | Go forward in browser history. |
| get_domC | Return the full page HTML source. |
| clickB | Click a DOM element by CSS selector. |
| type_textB | Clear an input and type text into it. |
| get_textB | Get the visible inner text of an element. |
| get_attributeB | Get an attribute value from a DOM element (e.g. href, value, class). |
| press_keyB | Press a keyboard key (e.g. Enter, Tab, Escape). Optionally target a specific element. |
| wait_forB | Wait until a CSS selector is visible on the page. |
| wait_for_dom_stableC | Wait until the DOM stops mutating (smart wait for AJAX content). |
| execute_jsC | Execute JavaScript in the browser and return the result. |
| screenshotC | Capture a base64-encoded PNG screenshot of the current viewport. |
| get_console_logsB | Return all captured browser console log entries. |
| get_network_logsC | Return all captured network request/response entries. |
| get_performance_metricsC | Return page performance timing data. |
| intercept_requestsC | Register a URL pattern for network interception (log or block). |
| windowC | Manage browser windows and tabs. Actions: list, switch, switch_latest, close. |
| frameC | Switch focus to a frame or back to the main page. Actions: switch, default. |
| alertB | Handle browser alert/confirm/prompt dialogs. Actions: accept, dismiss, get_text, send_text. |
| add_cookieC | Add a cookie. Browser must be on a page from the cookie's domain. |
| get_cookiesC | Get cookies. Returns all or a specific one by name. |
| delete_cookieC | Delete cookies. Deletes all or a specific one by name. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Current Page Accessibility Tree | A compact, structured JSON representation of interactive elements and text content on the current page. Much smaller than full HTML. Useful for understanding page layout and finding elements. |
| Browser Session Status | Returns the current browser session status including URL, title, window count, and active session info. |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/SCV-Consultants/selenium-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server